© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3493
    Prev
    Next
    INDEX
    Explanations

    indicators of obituaries or memorial announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bay
    -0.06
    ênh
    -0.06
    isp
    -0.06
     Lump
    -0.06
    929
    -0.06
     Braun
    -0.06
    strict
    -0.06
    angel
    -0.06
    дел
    -0.06
    ogh
    -0.06
    POSITIVE LOGITS
    erval
    0.07
    æĹı
    0.06
     Presidency
    0.06
     presidency
    0.06
    iversal
    0.06
     lev
    0.06
     readdir
    0.06
    encer
    0.06
     ÙģرزÙĨد
    0.06
    illez
    0.06
    Activations Density 0.001%

    No Known Activations